Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
SFT Generalization on Tulu3 SFT (Original)
Loading...
79.9
General Score
Qwen-7B + Tulu-Delta
68.4808
71.4454
74.41
77.3746
May 18, 2026
General Score
Updated 15d ago
Evaluation Results
Method
Method
Links
General Score
Qwen-7B + Tulu-Delta
Base Model=Qwen2.5-7B,...
2026.05
79.9
Dense-FT-Avg
Base Model=Qwen2.5-7B,...
2026.05
76.46
DeltaMoE
Base Model=Qwen2.5-7B,...
2026.05
76.14
LLaMA-Pro
Base Model=Qwen2.5-7B,...
2026.05
75.49
Dense-FT-Avg-2FLOPs
Base Model=Qwen2.5-7B,...
2026.05
75.27
MoLA
Base Model=Qwen2.5-7B,...
2026.05
74.59
Dense-FT-Delta
Base Model=Qwen2.5-7B,...
2026.05
72.6
Dense-FT-Delta-2FLOPs
Base Model=Qwen2.5-7B,...
2026.05
68.92
Feedback
Search any
task
Search any
task